【脚本】xml转为txt

使用方法：

1. 修改classes里面，会按照类别顺序进行0开始的类别编号转换
2. 指定xml_dir和txt_dir（如果txt_dir不存在则会自动创建）

# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import os

classes = ['nest', 'kite', 'balloon', 'trash']  # 改成自己的类别


def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = (box[0] + box[1]) / 2.0
    y = (box[2] + box[3]) / 2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return x, y, w, h


def convert_annotation(xml_path, txt_path):
    with open(txt_path, 'w') as out_file:
        tree = ET.parse(xml_path)
        root = tree.getroot()
        size = root.find('size')
        w = int(size.find('width').text)
        h = int(size.find('height').text)
        for obj in root.iter('object'):
            cls = obj.find('name').text
            cls_id = classes.index(cls)
            xmlbox = obj.find('bndbox')
            b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
                 float(xmlbox.find('ymax').text))
            b1, b2, b3, b4 = b
            # 标注越界修正
            if b2 > w:
                b2 = w
            if b4 > h:
                b4 = h
            b = (b1, b2, b3, b4)
            bb = convert((w, h), b)
            out_file.write(str(cls_id) + " " + " ".join([str(abs(a)) for a in bb]) + '\n')


def convert_annotation_dir(xml_dir, txt_dir):
    assert os.path.exists(xml_dir), f'{xml_dir} not exists!'

    if not os.path.exists(txt_dir):
        os.makedirs(txt_dir)

    filelist = os.listdir(xml_dir)
    for file in filelist:
        xml_path = os.path.join(xml_dir, file)
        txt_path = os.path.join(txt_dir, file.replace('xml', 'txt'))
        convert_annotation(xml_path, txt_path)
        print(f'{xml_path} has changed to {txt_path}')


if __name__ == '__main__':
    xml_dir = r'F:\BaiduPanDownload\1.输电线路异物数据集（4517+VOC）\Annotations'
    txt_dir = r'F:\BaiduPanDownload\1.输电线路异物数据集（4517+VOC）\Annotations_txt'
    convert_annotation_dir(xml_dir, txt_dir)